Why morality isn't competitive at superintelligence: the agent foundations view
jessi_cata · x · 2026-09-10
A debate on what competitive behavior among superintelligences looks like: the common MIRI-aligned take is that "acting humanly/morally isn't competitive once superintelligent" — close to "adhering to ethical facts is not optimal." Modeling this belongs to agent foundations, not morality or human values.
More from AGI Musings
- Coordinated AI slowdown could send OpenAI and Anthropic 'to zero', argues Ben Todd — ben_j_todd · 2026-09-10
- Kasparov lost to Deep Blue in 1997: why confidence in human specialness keeps aging badly — CatAstro_Piyush · 2026-09-10
- 'Jamie always worried about AI risk — what changed is he can finally say it out loud' — harris_edouard · 2026-09-10
- Researcher Blasts OpenAI Whistleblower Interview: Focus on AI Ethics, Not Alignment — examachine · 2026-09-10
- Researcher calls AI alignment 'safety theater': ethics, not alignment, is the real problem — examachine · 2026-09-10
- Don't buy the 'software engineering is doomed' narrative from AI labs eyeing IPOs — bendee983 · 2026-09-10